机构
*
Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院)
;
AIR, Tsinghua University(清华大学人工智能研究院)
;
BAAI(百度人工智能研究院)
;
The Hong Kong Polytechnic University(香港理工大学)
;
Nanjing University(南京大学)
;
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)(广东人工智能与数字经济实验室(深圳))
HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis
HVG-3D: 联接真实与仿真领域用于3D条件手-物体交互视频合成
Mingjin Chen, Junhao Chen, Zhaoxin Fan, Yujian Lee, Zichen Dang, Lili Wang, Yawen Cui, Lap-Pui Chau, Yi Wang
机构
*
Dept. of EEE, The Hong Kong Polytechnic University(香港理工大学电机及电子工程学系)
;
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, School of Artificial Intelligence, Beihang University(北京航空航天大学人工智能学院未来区块链与隐私计算北京高精尖创新中心)
;
Tsinghua University(清华大学)
;
Beijing Normal-Hong Kong Baptist University(北京师范大学-香港浸会大学联合国际学院)
;
State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院虚拟现实技术与系统国家重点实验室)
机构
*
Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
;
SSE, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)理工学院)
;
Pinscreen
LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models
LaVR:基于大规模4D重建模型的场景潜在条件生成视频轨迹重绘
Mingyang Xie, Numair Khan, Tianfu Wang, Naina Dhingra, Seonghyeon Nam, Haitao Yang, Zhuo Hui, Christopher Metzler, Andrea Vedaldi, Hamed Pirsiavash, Lei Luo
机构
*
Meta
;
University of Maryland(马里兰大学)
;
University of Oxford(牛津大学)
;
UC Davis(加州大学戴维斯分校)
Any4D: Open-Prompt 4D Generation from Natural Language and Images
Any4D: 从自然语言和图像生成开放提示的4D生成
Hao Li, Qiao Sun
专题命中
视频生成
:video generation(abstract);分类 cs.CV
AI总结
本文提出Primitive Embodied World Models,通过限制视频生成时间范围,实现语言与视觉表示的细粒度对齐,降低学习复杂度,提升数据效率,并减少推理延迟,支持复杂任务的组合泛化。
CommentsThe authors identified issues in the 4D generation pipeline and evaluation that affect result validity. To ensure scientific accuracy, we will revise the methodology and experiments thoroughly before resubmitting. This version should not be cited or relied upon